Emc IP Holding Company LLC

Michael Estrin

Zhen Jia

Jinpeng Liu

Kenneth Durazzo

Farida Shafik

Shary Beshara

Techniques for training data protection in an artificial intelligence model execution environment are disclosed. For example, a method comprises executing a first partition of an artificial intelligence model within a secure execution area of an information processing system and a second partition of the artificial intelligence model within a non-secure execution area of the information processing system, wherein data at least one of obtained and processed in the first partition of the artificial intelligence model is inaccessible to the second partition of the artificial intelligence model. Communication between the first partition and the second partition may be enabled via a model parallelism-based procedure. Data obtained in the secure execution area may comprise one or more data samples in an encrypted form usable to train the artificial intelligence model.

Training data protection for artificial intelligence model in partitioned execution environment

One example method includes extracting an expected communication specification of a service that is in development in a build pipeline, stimulating the service to exercise communication variations of the service, capturing communication traffic involving the service and one or more endpoints, comparing the captured communication traffic to the expected communication specification, and based on the comparing, detecting, in the captured communication traffic, and flagging, any anomalous communication behavior of the service.

Early validation of communication behavior

Techniques for training data protection in an artificial intelligence model execution environment are disclosed. For example, a method comprises executing a first portion of an artificial intelligence model within a trusted execution area of an information processing system and a second portion of the artificial intelligence model within an untrusted execution area of the information processing system, wherein data at least one of obtained and processed in the first portion of the artificial intelligence model is inaccessible to the second portion of the artificial intelligence model. Data obtained in the trusted execution area may comprise one or more data samples in an encrypted form usable to train the artificial intelligence model.

Training data protection in artificial intelligence model execution environment

Techniques for integrating a trusted execution platform with a function-based service framework are disclosed. For example, a method obtains an application program comprising a first set of one or more functions for execution within a secure execution area of a function-based service framework and a second set of one or more functions for execution within a non-secure execution area of the function-based service framework. A client attests an attestation delegator and the attestation delegator attests one or more secure containers prior to receipt of a function execution request to execute a function in the function-based service framework.

Growing community of inventors

Austin, TX, United States of America

Michael Estrin